Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    insurance and "avec"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isessä
    -0.08
     есте
    -0.08
     natürliche
    -0.08
     Sasha
    -0.08
     инф
    -0.08
     laste
    -0.07
     egyik
    -0.07
     holds
    -0.07
     өз
    -0.07
    势
    -0.07
    POSITIVE LOGITS
    Guarante
    0.10
    Enhanced
    0.09
     checksum
    0.09
    Added
    0.08
     verzekerd
    0.08
     guarantee
    0.08
    Ensure
    0.08
    Checksum
    0.08
     treasure
    0.08
     anguish
    0.08
    Act Density 0.008%

    No Known Activations